A Texture Feature Removal Network for Sonar Image Classification and Detection
Deep neural network (DNN) was applied in sonar image target recognition tasks, but it is very difficult to obtain enough sonar images that contain a target; as a result, the direct use of a small amount of data to train a DNN will cause overfitting and other problems. Transfer learning is the most e...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-01-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/15/3/616 |
| _version_ | 1797623356897361920 |
|---|---|
| author | Chuanlong Li Xiufen Ye Jier Xi Yunpeng Jia |
| author_facet | Chuanlong Li Xiufen Ye Jier Xi Yunpeng Jia |
| author_sort | Chuanlong Li |
| collection | DOAJ |
| description | Deep neural network (DNN) was applied in sonar image target recognition tasks, but it is very difficult to obtain enough sonar images that contain a target; as a result, the direct use of a small amount of data to train a DNN will cause overfitting and other problems. Transfer learning is the most effective way to address such scenarios. However, there is a large domain gap between optical images and sonar images, and common transfer learning methods may not be able to effectively handle it. In this paper, we propose a transfer learning method for sonar image classification and object detection called the texture feature removal network. We regard the texture features of an image as domain-specific features, and we narrow the domain gap by discarding the domain-specific features, and hence, make it easier to complete knowledge transfer. Our method can be easily embedded into other transfer learning methods, which makes it easier to apply to different application scenarios. Experimental results show that our method is effective in side-scan sonar image classification tasks and forward-looking sonar image detection tasks. For side-scan sonar image classification tasks, the classification accuracy of our method is enhanced by 4.5% in a supervised learning experiment, and for forward-looking sonar detection tasks, the average precision (AP) is also significantly improved. |
| first_indexed | 2024-03-11T09:27:45Z |
| format | Article |
| id | doaj.art-d3566e5049e547bd844f423433fe7015 |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-11T09:27:45Z |
| publishDate | 2023-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-d3566e5049e547bd844f423433fe70152023-11-16T17:51:52ZengMDPI AGRemote Sensing2072-42922023-01-0115361610.3390/rs15030616A Texture Feature Removal Network for Sonar Image Classification and DetectionChuanlong Li0Xiufen Ye1Jier Xi2Yunpeng Jia3College of Intelligent Systems Science and Engineering, Harbin Engineering University, Harbin 150009, ChinaCollege of Intelligent Systems Science and Engineering, Harbin Engineering University, Harbin 150009, ChinaCollege of Intelligent Systems Science and Engineering, Harbin Engineering University, Harbin 150009, ChinaCollege of Intelligent Systems Science and Engineering, Harbin Engineering University, Harbin 150009, ChinaDeep neural network (DNN) was applied in sonar image target recognition tasks, but it is very difficult to obtain enough sonar images that contain a target; as a result, the direct use of a small amount of data to train a DNN will cause overfitting and other problems. Transfer learning is the most effective way to address such scenarios. However, there is a large domain gap between optical images and sonar images, and common transfer learning methods may not be able to effectively handle it. In this paper, we propose a transfer learning method for sonar image classification and object detection called the texture feature removal network. We regard the texture features of an image as domain-specific features, and we narrow the domain gap by discarding the domain-specific features, and hence, make it easier to complete knowledge transfer. Our method can be easily embedded into other transfer learning methods, which makes it easier to apply to different application scenarios. Experimental results show that our method is effective in side-scan sonar image classification tasks and forward-looking sonar image detection tasks. For side-scan sonar image classification tasks, the classification accuracy of our method is enhanced by 4.5% in a supervised learning experiment, and for forward-looking sonar detection tasks, the average precision (AP) is also significantly improved.https://www.mdpi.com/2072-4292/15/3/616side-scan sonar image classificationforward-looking sonar image detectiontransfer learningdeep learningdomain specific feature |
| spellingShingle | Chuanlong Li Xiufen Ye Jier Xi Yunpeng Jia A Texture Feature Removal Network for Sonar Image Classification and Detection Remote Sensing side-scan sonar image classification forward-looking sonar image detection transfer learning deep learning domain specific feature |
| title | A Texture Feature Removal Network for Sonar Image Classification and Detection |
| title_full | A Texture Feature Removal Network for Sonar Image Classification and Detection |
| title_fullStr | A Texture Feature Removal Network for Sonar Image Classification and Detection |
| title_full_unstemmed | A Texture Feature Removal Network for Sonar Image Classification and Detection |
| title_short | A Texture Feature Removal Network for Sonar Image Classification and Detection |
| title_sort | texture feature removal network for sonar image classification and detection |
| topic | side-scan sonar image classification forward-looking sonar image detection transfer learning deep learning domain specific feature |
| url | https://www.mdpi.com/2072-4292/15/3/616 |
| work_keys_str_mv | AT chuanlongli atexturefeatureremovalnetworkforsonarimageclassificationanddetection AT xiufenye atexturefeatureremovalnetworkforsonarimageclassificationanddetection AT jierxi atexturefeatureremovalnetworkforsonarimageclassificationanddetection AT yunpengjia atexturefeatureremovalnetworkforsonarimageclassificationanddetection AT chuanlongli texturefeatureremovalnetworkforsonarimageclassificationanddetection AT xiufenye texturefeatureremovalnetworkforsonarimageclassificationanddetection AT jierxi texturefeatureremovalnetworkforsonarimageclassificationanddetection AT yunpengjia texturefeatureremovalnetworkforsonarimageclassificationanddetection |